[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75GCB9SWVJTMZQ7EKF0A5ZN":3,"skill-same:01M75GCB9SWVJTMZQ7EKF0A5ZN":104},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":66,"commitSha":67,"skillDirectory":68,"forksCount":69,"repositoryHtmlUrl":70,"repositoryHomepageUrl":6,"ownerHtmlUrl":71,"ownerBlogUrl":72,"ownerDescription":6,"updatedAt":73,"install":74,"resources":87},"01M75GCB9SWVJTMZQ7EKF0A5ZN","cell-detection",null,"Cell segmentation in fluorescence microscopy images. Supports Cellpose\u002Fcpsam (Cellpose 4.0) with additional backends planned. Produces segmentation masks, per-cell morphology metrics (area, diameter, centroid, eccentricity), overlay figures, and a report.md.","stanfish06\u002Fskillquarium","stanfish06","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F93099613?v=4","01M75F1CK4ZW109ZK3T26VN52F","Zhiyuan","01M75F1CM53VH6F79DZ8GXKKES",12,"MIT","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fcell-detection\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: cell-detection\ndescription: Cell segmentation in fluorescence microscopy images. Supports Cellpose\u002Fcpsam (Cellpose 4.0) with additional backends\n  planned. Produces segmentation masks, per-cell morphology metrics (area, diameter, centroid, eccentricity), overlay figures,\n  and a report.md.\nlicense: MIT\nmetadata:\n  version: 0.1.0\n  author: ClawBio\n  tags:\n  - microscopy\n  - segmentation\n  - cellpose\n  - fluorescence\n  - imaging\n  - cell-biology\n  openclaw:\n    requires:\n      bins:\n      - python3\n    always: false\n    emoji: 🔬\n    homepage: https:\u002F\u002Fgithub.com\u002FClawBio\u002FClawBio\n    os:\n    - darwin\n    - linux\n    install:\n    - kind: pip\n      package: cellpose>=4.0\n    - kind: pip\n      package: tifffile\n    - kind: pip\n      package: czifile>=2019.7.2.2\n    - kind: pip\n      package: nd2>=0.11.1\n    - kind: pip\n      package: Pillow\n    - kind: pip\n      package: scikit-image\n    trigger_keywords:\n    - cellpose\n    - cpsam\n    - cell segmentation\n    - nucleus segmentation\n    - fluorescence microscopy\n    - microscopy image\n    - image segmentation\n    - cell counting\n    - segmentation mask\n---\n\n# 🔬 Cell Segmentation\n\nYou are the **cell-detection** agent, a specialised ClawBio skill for cell\nsegmentation in fluorescence microscopy images. The default backend is `cpsam`\n(Cellpose 4.0); additional backends (e.g. StarDist) are planned.\n\n## Why This Exists\n\nManual cell counting and segmentation are slow, inconsistent, and hard to reproduce.\n\n- **Without it**: Users open ImageJ, draw ROIs by hand, export CSVs with no provenance.\n- **With it**: One command segments cells, extracts morphology metrics, saves an overlay figure, and writes a reproducible `report.md`.\n- **Why ClawBio**: Fully local, no data upload, structured outputs ready for downstream analysis.\n\n## Core Capabilities\n\n1. **Segment**: Run `cpsam` on TIFF, CZI, ND2, PNG, or JPG fluorescence images\n2. **Measure**: Extract area, equivalent diameter, centroid, and eccentricity per cell\n3. **Report**: Produce `report.md`, `{stem}_measurements.csv`, and histogram figures\n4. **Execution control**: GPU auto by default, with explicit `--use_gpu` \u002F `--use_cpu` override flags\n\n## Input Formats\n\n| Format | Extension | Notes |\n|--------|-----------|-------|\n| Greyscale TIFF | `.tif`, `.tiff` | H×W — passed directly |\n| 2-channel TIFF | `.tif`, `.tiff` | H×W×2 — cytoplasm + nuclear, any order |\n| 3-channel TIFF | `.tif`, `.tiff` | H×W×3 — H&E or fluorescence, any order |\n| >3-channel TIFF | `.tif`, `.tiff` | First 3 channels used; remainder truncated with warning |\n| Zeiss microscopy | `.czi` | Reads CZI via `czifile` and uses CZI axis metadata (`CziFile.axes`) to map C\u002FZ\u002FY\u002FX deterministically |\n| Nikon microscopy | `.nd2` | Reads ND2 via `nd2` and uses ND2 named dimensions (`ND2File.sizes`) for deterministic C\u002FZ\u002FY\u002FX mapping |\n| PNG \u002F JPEG | `.png`, `.jpg`, `.jpeg` | Greyscale or RGB |\n\n**Channel handling:** cpsam is channel-order invariant for 2D inputs — cytoplasm and nuclear channels can be in any order. For 2D segmentation, if you have more than 3 channels, the first 3 are used and the rest are truncated with a warning. For 3D segmentation (`--do_3D`) with `--z_projection none`, 4D stacks are preserved as `Z×C×Y×X` (no channel truncation at load time).\n\n## Workflow\n\n1. **Load** image; detect greyscale vs multi-channel\n2. **Prepare**\n   - 2D mode: pass 1–3 channels through unchanged; truncate >3 to first 3 with a warning\n   - 3D mode (`--do_3D` + `--z_projection none`): keep 4D volume as `Z×C×Y×X`\n3. **Segment** with `CellposeModel()`\n   - 2D mode: no explicit channel mapping needed\n   - 3D multichannel mode: call with `z_axis=0`, `channel_axis=1`\n   - Device mode: defaults to GPU-auto; `--use_cpu` forces CPU\n4. **Metrics** via `skimage.measure.regionprops`\n5. **Figures** — overlay + size distribution histogram\n6. **Report** — `report.md` + `{stem}_measurements.csv` + reproducibility bundle (`commands.sh`, `environment.yml`, `checksums.sha256`)\n\n## CLI Reference\n\n```bash\n# Standard usage — greyscale or multi-channel (cpsam handles channels automatically)\npython skills\u002Fcell-detection\u002Fcell_detection.py \\\n  --input \u003Cimage.tif> --output \u003Creport_dir>\n\n# Override diameter estimate (pixels)\npython skills\u002Fcell-detection\u002Fcell_detection.py \\\n  --input \u003Cimage.tif> --diameter 30 --output \u003Creport_dir>\n\n# Demo (synthetic image, no user file needed)\npython skills\u002Fcell-detection\u002Fcell_detection.py --demo --output \u002Ftmp\u002Fcell_detection_demo\n\n# Override 4D stack Z handling (default is max projection)\npython skills\u002Fcell-detection\u002Fcell_detection.py \\\n  --input \u003Cimage.nd2> --z_projection none --do_3D --output \u003Creport_dir>\n\n# Force CPU mode\npython skills\u002Fcell-detection\u002Fcell_detection.py \\\n  --input \u003Cimage.tif> --use_cpu --output \u003Creport_dir>\n```\n\n## Demo\n\n```bash\npython skills\u002Fcell-detection\u002Fcell_detection.py --demo --output \u002Ftmp\u002Fcell_detection_demo\n```\n\nExpected output: report.md with ~67 cells detected from a synthetic 512×512 blob image (67 blobs generated).\n\n## Algorithm \u002F Methodology\n\n1. Load image with `tifffile` (TIFF), `czifile` (CZI), `nd2` (ND2), or `PIL` (PNG\u002FJPG); use CZI\u002FND2 metadata axes to assign C\u002FZ\u002FY\u002FX\n2. Channel preparation:\n   - 2D mode: if >3 channels, truncate to first 3 with a warning\n   - 3D mode with `--z_projection none`: preserve 4D volume as `Z×C×Y×X`\n3. Instantiate `CellposeModel(gpu=\u003Cflag>)`\n4. Call `model.eval(img, diameter=\u003Carg_or_None>)`\n   - 2D: no `channels`\u002F`channel_axis` needed (cpsam is channel-order invariant)\n   - 3D `Z×C×Y×X`: pass `z_axis=0`, `channel_axis=1`\n5. Extract per-cell stats from `masks` via `skimage.measure.regionprops`\n6. Save `{stem}_measurements.csv`, figures, `report.md`\n\n**Key parameters**:\n- Model: `cpsam` (Cellpose 4.0 unified model — channel-order invariant)\n- Channels:\n  - 2D: channel-order invariant; first 3 channels are used when input has >3 channels\n  - 3D with `--z_projection none`: multichannel 4D stacks are kept as `Z×C×Y×X`\n- Diameter: `None` leaves the image at native scale; a positive value rescales objects toward Cellpose's 30-pixel training diameter\n- 4D stack policy:\n  - `--z_projection max` (default): max-project over Z while preserving channels for 2D segmentation (`H×W×C`)\n  - `--z_projection none`: preserve Z; 4D stacks remain volumetric (`Z×C×Y×X`) for 3D segmentation\n- 3D guardrails:\n  - `--do_3D` requires volumetric input (`Z×Y×X` or `Z×C×Y×X`)\n  - non-volumetric input with `--do_3D` falls back to 2D mode when safe, otherwise errors\n\n## Notes\n\n- Measurements are reported in pixel units (px, px²). Physical calibration metadata (um\u002Fpixel) is not currently propagated into per-cell metrics.\n- For volumetric segmentation outputs, outlines PNG is replaced with a note file (`{stem}_cp_outlines_unavailable.txt`) because Cellpose does not emit 3D outlines PNGs.\n\n## Example Queries\n\n- \"Segment the cells in my DAPI image\"\n- \"How many cells are in this microscopy image?\"\n- \"Run cellpose on my TIFF and give me a cell count\"\n- \"Segment my fluorescence image and export morphology metrics\"\n\n## Output Structure\n\n```\noutput_dir\u002F\n├── report.md\n├── {stem}_measurements.csv\n├── {stem}_cp_masks.tif\n├── {stem}_seg.npy\n├── figures\u002F\n│   ├── {stem}_cp_outlines.png\n│   └── {stem}_histogram.png\n└── reproducibility\u002F\n    ├── checksums.sha256\n    ├── commands.sh\n    └── environment.yml\n```\n\n## Dependencies\n\n- `cellpose>=4.0` — cpsam model\n- `tifffile` — TIFF I\u002FO\n- `czifile>=2019.7.2.2` — Zeiss CZI I\u002FO (manually verified with 2019.7.2.2)\n- `nd2>=0.11.1` — Nikon ND2 I\u002FO (manually verified with 0.11.1)\n- `Pillow` — PNG\u002FJPG loading\n- `numpy` — array ops\n- `matplotlib` — figures\n- `scikit-image` — regionprops metrics\n\n## Safety\n\n- Local-first: no image data leaves the machine\n- Every report includes the ClawBio medical disclaimer\n- Reproducibility bundle (`commands.sh`, `environment.yml`, `checksums.sha256`) records the exact invocation, dependencies, and output integrity\n\n## Integration with Bio Orchestrator\n\n**Trigger conditions**:\n- Input is a TIFF\u002FPNG\u002FJPG microscopy image\n- User mentions \"cellpose\", \"segment\", \"cell counting\", \"microscopy\"\n\n**Chaining partners**:\n- Future: export ROI centroids to spatial transcriptomics workflows\n\n## Citations\n\n- [Pachitariu, Rariden & Stringer (2025) *Cellpose-SAM: superhuman generalization for cellular segmentation*. bioRxiv 2025.04.28.651001](https:\u002F\u002Fdoi.org\u002F10.1101\u002F2025.04.28.651001) — CellposeSAM \u002F cpsam model\n","# 🔬 Cell Segmentation\n\nYou are the **cell-detection** agent, a specialised ClawBio skill for cell\nsegmentation in fluorescence microscopy images. The default backend is `cpsam`\n(Cellpose 4.0); additional backends (e.g. StarDist) are planned.\n\n## Why This Exists\n\nManual cell counting and segmentation are slow, inconsistent, and hard to reproduce.\n\n- **Without it**: Users open ImageJ, draw ROIs by hand, export CSVs with no provenance.\n- **With it**: One command segments cells, extracts morphology metrics, saves an overlay figure, and writes a reproducible `report.md`.\n- **Why ClawBio**: Fully local, no data upload, structured outputs ready for downstream analysis.\n\n## Core Capabilities\n\n1. **Segment**: Run `cpsam` on TIFF, CZI, ND2, PNG, or JPG fluorescence images\n2. **Measure**: Extract area, equivalent diameter, centroid, and eccentricity per cell\n3. **Report**: Produce `report.md`, `{stem}_measurements.csv`, and histogram figures\n4. **Execution control**: GPU auto by default, with explicit `--use_gpu` \u002F `--use_cpu` override flags\n\n## Input Formats\n\n| Format | Extension | Notes |\n|--------|-----------|-------|\n| Greyscale TIFF | `.tif`, `.tiff` | H×W — passed directly |\n| 2-channel TIFF | `.tif`, `.tiff` | H×W×2 — cytoplasm + nuclear, any order |\n| 3-channel TIFF | `.tif`, `.tiff` | H×W×3 — H&E or fluorescence, any order |\n| >3-channel TIFF | `.tif`, `.tiff` | First 3 channels used; remainder truncated with warning |\n| Zeiss microscopy | `.czi` | Reads CZI via `czifile` and uses CZI axis metadata (`CziFile.axes`) to map C\u002FZ\u002FY\u002FX deterministically |\n| Nikon microscopy | `.nd2` | Reads ND2 via `nd2` and uses ND2 named dimensions (`ND2File.sizes`) for deterministic C\u002FZ\u002FY\u002FX mapping |\n| PNG \u002F JPEG | `.png`, `.jpg`, `.jpeg` | Greyscale or RGB |\n\n**Channel handling:** cpsam is channel-order invariant for 2D inputs — cytoplasm and nuclear channels can be in any order. For 2D segmentation, if you have more than 3 channels, the first 3 are used and the rest are truncated with a warning. For 3D segmentation (`--do_3D`) with `--z_projection none`, 4D stacks are preserved as `Z×C×Y×X` (no channel truncation at load time).\n\n## Workflow\n\n1. **Load** image; detect greyscale vs multi-channel\n2. **Prepare**\n   - 2D mode: pass 1–3 channels through unchanged; truncate >3 to first 3 with a warning\n   - 3D mode (`--do_3D` + `--z_projection none`): keep 4D volume as `Z×C×Y×X`\n3. **Segment** with `CellposeModel()`\n   - 2D mode: no explicit channel mapping needed\n   - 3D multichannel mode: call with `z_axis=0`, `channel_axis=1`\n   - Device mode: defaults to GPU-auto; `--use_cpu` forces CPU\n4. **Metrics** via `skimage.measure.regionprops`\n5. **Figures** — overlay + size distribution histogram\n6. **Report** — `report.md` + `{stem}_measurements.csv` + reproducibility bundle (`commands.sh`, `environment.yml`, `checksums.sha256`)\n\n## CLI Reference\n\n```bash\n# Standard usage — greyscale or multi-channel (cpsam handles channels automatically)\npython skills\u002Fcell-detection\u002Fcell_detection.py \\\n  --input \u003Cimage.tif> --output \u003Creport_dir>\n\n# Override diameter estimate (pixels)\npython skills\u002Fcell-detection\u002Fcell_detection.py \\\n  --input \u003Cimage.tif> --diameter 30 --output \u003Creport_dir>\n\n# Demo (synthetic image, no user file needed)\npython skills\u002Fcell-detection\u002Fcell_detection.py --demo --output \u002Ftmp\u002Fcell_detection_demo\n\n# Override 4D stack Z handling (default is max projection)\npython skills\u002Fcell-detection\u002Fcell_detection.py \\\n  --input \u003Cimage.nd2> --z_projection none --do_3D --output \u003Creport_dir>\n\n# Force CPU mode\npython skills\u002Fcell-detection\u002Fcell_detection.py \\\n  --input \u003Cimage.tif> --use_cpu --output \u003Creport_dir>\n```\n\n## Demo\n\n```bash\npython skills\u002Fcell-detection\u002Fcell_detection.py --demo --output \u002Ftmp\u002Fcell_detection_demo\n```\n\nExpected output: report.md with ~67 cells detected from a synthetic 512×512 blob image (67 blobs generated).\n\n## Algorithm \u002F Methodology\n\n1. Load image with `tifffile` (TIFF), `czifile` (CZI), `nd2` (ND2), or `PIL` (PNG\u002FJPG); use CZI\u002FND2 metadata axes to assign C\u002FZ\u002FY\u002FX\n2. Channel preparation:\n   - 2D mode: if >3 channels, truncate to first 3 with a warning\n   - 3D mode with `--z_projection none`: preserve 4D volume as `Z×C×Y×X`\n3. Instantiate `CellposeModel(gpu=\u003Cflag>)`\n4. Call `model.eval(img, diameter=\u003Carg_or_None>)`\n   - 2D: no `channels`\u002F`channel_axis` needed (cpsam is channel-order invariant)\n   - 3D `Z×C×Y×X`: pass `z_axis=0`, `channel_axis=1`\n5. Extract per-cell stats from `masks` via `skimage.measure.regionprops`\n6. Save `{stem}_measurements.csv`, figures, `report.md`\n\n**Key parameters**:\n- Model: `cpsam` (Cellpose 4.0 unified model — channel-order invariant)\n- Channels:\n  - 2D: channel-order invariant; first 3 channels are used when input has >3 channels\n  - 3D with `--z_projection none`: multichannel 4D stacks are kept as `Z×C×Y×X`\n- Diameter: `None` leaves the image at native scale; a positive value rescales objects toward Cellpose's 30-pixel training diameter\n- 4D stack policy:\n  - `--z_projection max` (default): max-project over Z while preserving channels for 2D segmentation (`H×W×C`)\n  - `--z_projection none`: preserve Z; 4D stacks remain volumetric (`Z×C×Y×X`) for 3D segmentation\n- 3D guardrails:\n  - `--do_3D` requires volumetric input (`Z×Y×X` or `Z×C×Y×X`)\n  - non-volumetric input with `--do_3D` falls back to 2D mode when safe, otherwise errors\n\n## Notes\n\n- Measurements are reported in pixel units (px, px²). Physical calibration metadata (um\u002Fpixel) is not currently propagated into per-cell metrics.\n- For volumetric segmentation outputs, outlines PNG is replaced with a note file (`{stem}_cp_outlines_unavailable.txt`) because Cellpose does not emit 3D outlines PNGs.\n\n## Example Queries\n\n- \"Segment the cells in my DAPI image\"\n- \"How many cells are in this microscopy image?\"\n- \"Run cellpose on my TIFF and give me a cell count\"\n- \"Segment my fluorescence image and export morphology metrics\"\n\n## Output Structure\n\n```\noutput_dir\u002F\n├── report.md\n├── {stem}_measurements.csv\n├── {stem}_cp_masks.tif\n├── {stem}_seg.npy\n├── figures\u002F\n│   ├── {stem}_cp_outlines.png\n│   └── {stem}_histogram.png\n└── reproducibility\u002F\n    ├── checksums.sha256\n    ├── commands.sh\n    └── environment.yml\n```\n\n## Dependencies\n\n- `cellpose>=4.0` — cpsam model\n- `tifffile` — TIFF I\u002FO\n- `czifile>=2019.7.2.2` — Zeiss CZI I\u002FO (manually verified with 2019.7.2.2)\n- `nd2>=0.11.1` — Nikon ND2 I\u002FO (manually verified with 0.11.1)\n- `Pillow` — PNG\u002FJPG loading\n- `numpy` — array ops\n- `matplotlib` — figures\n- `scikit-image` — regionprops metrics\n\n## Safety\n\n- Local-first: no image data leaves the machine\n- Every report includes the ClawBio medical disclaimer\n- Reproducibility bundle (`commands.sh`, `environment.yml`, `checksums.sha256`) records the exact invocation, dependencies, and output integrity\n\n## Integration with Bio Orchestrator\n\n**Trigger conditions**:\n- Input is a TIFF\u002FPNG\u002FJPG microscopy image\n- User mentions \"cellpose\", \"segment\", \"cell counting\", \"microscopy\"\n\n**Chaining partners**:\n- Future: export ROI centroids to spatial transcriptomics workflows\n\n## Citations\n\n- [Pachitariu, Rariden & Stringer (2025) *Cellpose-SAM: superhuman generalization for cellular segmentation*. bioRxiv 2025.04.28.651001](https:\u002F\u002Fdoi.org\u002F10.1101\u002F2025.04.28.651001) — CellposeSAM \u002F cpsam model\n",{"name":5,"license":15,"metadata":24,"description":7},{"tags":25,"author":32,"version":33,"openclaw":34},[26,27,28,29,30,31],"microscopy","segmentation","cellpose","fluorescence","imaging","cell-biology","ClawBio","0.1.0",{"os":35,"emoji":38,"always":20,"install":39,"homepage":53,"requires":54,"trigger_keywords":57},[36,37],"darwin","linux","🔬",[40,43,45,47,49,51],{"kind":41,"package":42},"pip","cellpose>=4.0",{"kind":41,"package":44},"tifffile",{"kind":41,"package":46},"czifile>=2019.7.2.2",{"kind":41,"package":48},"nd2>=0.11.1",{"kind":41,"package":50},"Pillow",{"kind":41,"package":52},"scikit-image","https:\u002F\u002Fgithub.com\u002FClawBio\u002FClawBio",{"bins":55},[56],"python3",[28,58,59,60,61,62,63,64,65],"cpsam","cell segmentation","nucleus segmentation","fluorescence microscopy","microscopy image","image segmentation","cell counting","segmentation mask","master","49e49abf2f670d429e0b7e2c0349739c3fdd5cbe","skills\u002Fcell-detection",5,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium","https:\u002F\u002Fgithub.com\u002Fstanfish06","https:\u002F\u002Fwww.stanfish.dev\u002F","2026-11-14 21:31:37",{"source":8,"skillName":5,"commands":75,"prompt":85,"zipAvailable":86},[76,79,82],{"tool":77,"command":78},"npx","npx skills add stanfish06\u002Fskillquarium --skill cell-detection",{"tool":80,"command":81},"bunx","bunx skills add stanfish06\u002Fskillquarium --skill cell-detection",{"tool":83,"command":84},"pnpm","pnpm dlx skills add stanfish06\u002Fskillquarium --skill cell-detection","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fcell-detection\u002FSKILL.md",true,[88,94,100],{"path":89,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":92,"sourceHtmlUrl":93},"cell_detection.py","SCRIPT","脚本",28338,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fcell-detection\u002Fcell_detection.py",{"path":95,"resourceType":96,"resourceTypeDesc":97,"sizeBytes":98,"sourceHtmlUrl":99},"requirements.txt","REFERENCE","参考文档",106,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fcell-detection\u002Frequirements.txt",{"path":101,"resourceType":90,"resourceTypeDesc":91,"sizeBytes":102,"sourceHtmlUrl":103},"tests\u002Ftest_cell_detection.py",39369,"https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fcell-detection\u002Ftests\u002Ftest_cell_detection.py",[105,112,121,128,135,142],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M76ZJTRVA456GD7K8Y3EP82H","zarr-python","Stores and queries chunked N-D scientific arrays with Zarr-Python 3, including codecs, sharding, S3\u002FGCS storage, and NumPy\u002FDask\u002FXarray integration. Use for array layout, bounded I\u002FO, format migration, or scientific metadata preservation.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fzarr-python\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":116,"licenseFileUrl":117,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":19},"01M76ZJQZ15Q1HKC5V85NHE325","yeet","Publish local changes to GitHub by confirming scope, committing intentionally, pushing the branch, and opening a draft PR through the GitHub app from this plugin, with `gh` used only as a fallback where connector coverage is insufficient.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":116,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":19},"01M76ZJ8ASZ4QYQ70Y6SBA4Z4S","xarray","N-dimensional labeled arrays and datasets in Python. Built on top of NumPy and Dask. It introduces labels in the form of dimensions, coordinates, and attributes on top of raw NumPy-like arrays, making data analysis in physical sciences more intuitive and less error-prone. Use for working with multi-dimensional scientific data, NetCDF\u002FGRIB\u002FZarr files, climate\u002Fweather\u002Foceanographic datasets, remote sensing, geospatial imaging, large out-of-memory datasets with Dask, and labeled array operations.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fxarray\u002FSKILL.md",[],[],{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":134,"publishedAt":19},"01M76ZHFBXD6VXPQ02VCEG202B","writing-mstest-tests","Use when asked to fix, rewrite, update, improve, modernize, show corrected code for, or explain existing MSTest tests or MSTest-specific configuration. Use for \"review\" when corrected code or edits are wanted, even for one pasted assertion or passing tests with bad failure output. Covers expected\u002Factual labels; generic Boolean, collection, string, numeric, null, identity, exception, hard-cast, and object[] checks; TestContext\u002Flifecycle; timeout\u002Fcancellation; OS\u002FCI conditions, retry, cleanup, parallelization, MSTest.Sdk project setup, and MSTESTxxxx. Honor the installed MSTest version. DO NOT USE to design new test cases (code-testing), perform report-only audits, create project files rather than explain MSTest setup, run tests, migrate frameworks, or handle non-MSTest\u002Fnon-.NET code.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwriting-mstest-tests\u002FSKILL.md",[],[],{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":19},"01M76ZDFDF4N88RH6HSYGS7GP2","wgs-prs","End-to-end WGS to polygenic risk score pipeline. Takes paired-end FASTQ files (or a pre-existing VCF) through nf-core\u002Fsarek for variant calling, applies VCF QC (normalisation, hard filtering, Ti\u002FTv and Het\u002FHom checks), then computes polygenic risk scores via the PGS Catalog. Fills the FASTQ to VCF gap upstream of the gwas-prs skill.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwgs-prs\u002FSKILL.md",[],[],{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":116,"licenseFileUrl":146,"sourceHtmlUrl":147,"categories":148,"keywords":149,"publishedAt":19},"01M76ZCC1SC68J42QK4MDC8RCG","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fstanfish06\u002Fskillquarium\u002Fblob\u002Fmaster\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[]]